Datasets
DATASETGitHub
5/5

The FLORES-200 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation

Nuer(nus)TextMTEast Africa
View Source

Dataset Info

Language
Nuer (nus)
Modality
Text
Domain
General
Size
—
Institution
GitHub
Last Updated
26 May 2026

License & Access

SPDX identifierUnknown

License unknown — use with caution until an SPDX identifier is confirmed.

RedistributionAllowed

PII RISK

Unknown risk

Full Record

19 of 46 fields stated

Every column the registry tracks. Values marked derivedwere filled by a rule or read from the source's text rather than stated in its metadata; the rule or the quoted sentence is shown under the value.

Registry columns (16/27)

iso code
nus
Dataset name
The FLORES-200 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation
Modality
Text
Type
dataset
Link
https://github.com/facebookresearch/flores/tree/main/flores200
NLP Task
MT
Domain
General
Data Format
Not stated
Size Metric
Not stated
Size Value
Not stated
License
Not stated
Open Access
Open
Source Repository
GitHub
Year Published
Not stated
Creator/Author(s)
Not stated
Funder/Partner
Other
Dialect Coverage
Standard
Gender Balance
Not stated
Speaker Count
Not stated
Annotation Type
Not stated
Status
Active
Has Datasheet
No
PII Risk
Not stated
Consent Verified
Not stated
Verified By
Lanfrica Pipeline
Date Indexed
2026-05-26
Notes / Flags
Parsed from Lanfrica name: the-flores-200-evaluation-benchmark-for-low-resource-and-multilingual-machine-translation.

Quality (DQI) (2/12)

Datasheet Fields Completed
Not stated
SPDX License ID
Not stated
Redistribution Allowed?
Not stated
Content Hash
Not stated
Submitted By
LanAfrica pipeline (automated)
Fetch Date
2026-05-26
Last Updated Date
Not stated
Annotation Guidelines Available?
Not stated
IAA Score
Not stated
Cleaning Notes
Not stated
Benchmark Exists?
Not stated
Benchmark Citation
Not stated

Representativeness (DRI) (1/7)

Gender Distribution
Not stated
Region Coverage
Not stated
Region Distribution
Not stated
Age Range Coverage
Not stated
Register
Not stated
Marginalized Group Note
Not stated
Demographic Fields Reported Count
0

Readiness Score Breakdown

5/5
Data Coverage100%
Model Availability100%
Benchmarks100%
Documentation85%
Recency100%

Representativeness

Gender Balance
Regional Distribution
Dialect Coverage
Inclusivity

Provenance

Source URL
https://github.com/facebookresearch/flores/tree/main/flores200
Fetch Timestamp
26 May 2026
Content Hash
—

Audit Log

Record indexed from GitHub

26 May 2026

Source status: Active

26 May 2026

Other Copies

This is a copy of the resource below, which the platform counts and shows in search.

dataset

FLORES-200 (facebook/flores)

Original FLORES-200 evaluation set covering nus among 200+ languages; HuggingFace card explicitly states this repo 'is no longer being updated' and points to…

59 languages4 copiesNuer(nus)TextMT
HUHugging Face
Open31 Jul 2026
dataset

flores

Data format: parquet

59 languages4 copiesNuer(nus)Texttranslation
HUHugging Face
Open27 Oct 2026
dataset

flores

text2text-generation, translation · NLP (Health, Social Media) domain · meer3305

59 languages4 copiesNuer(nus)Nlptext2text-generation, translation
HUHugging Face
Open27 Oct 2026

Also Available In

This is the same multilingual corpus, sliced for other languages the platform indexes it under.

dataset

flores

Data format: parquet

59 languages4 copiesTunisian Arabic(aeb)Tabulartext-generation, translation
HUHugging Face
Open27 Oct 2026
dataset

FLORES-200 (afr_Latn)

Used in 200-language MT benchmark

59 languages4 copiesAfrikaans(afr)TextMT
HUHugging Face
Open11 May 2026
dataset

flores

Data format: parquet

59 languages4 copiesAmharic(amh)Tabulartext-generation, translation
HUHugging Face
Open27 Oct 2026
dataset

FLORES-200 (ary_Arab)

Moroccan Arabic in 200-language MT benchmark

59 languages4 copiesMoroccan Arabic (Darija)(ary)TextMT
HUHugging Face
Open11 May 2026
dataset

flores

Data format: parquet

59 languages4 copiesEgyptian Arabic(arz)Tabulartext-generation, translation
HUHugging Face
Open27 Oct 2026
dataset

flores

Data format: parquet

59 languages4 copiesBambara(bam)Tabulartext-generation, translation
HUHugging Face
Open27 Oct 2026
dataset

FLORES-200 – Ghomálá' MT Evaluation Corpus (bbj_Latn)

997 dev + 1,012 devtest sentences; human-translated from English; backbone of NLLB MT evaluation; Nature 2024 doi:10.1038/s41586-024-07335-x

59 languages4 copiesGhomálá'(bbj)TextMT
HUHugging Face
Open22 May 2025
dataset

FLORES-200 Bemba

"Multilingual MT evaluation corpus includes Bemba"

59 languages4 copiesBemba(bem)TextMT
HUHugging Face
Open5 Jun 2026
dataset

FLORES-200 Bena

"Language code bez represented in FLORES-200"

59 languages4 copiesBena(bez)TextMT
HUHugging Face
Open5 Jun 2026
dataset

FLORES-200 (nus_Latn / Bari cluster)

Bari partially covered in FLORES under Nuer/Bari cluster; verify nus_Latn

59 languages4 copiesBari(bfa)TextMT
HUHugging Face
Open13 May 2026
dataset

FLORES-200 (cjk_Latn)

Chokwe (cjk_Latn) in 200-language MT benchmark

59 languages4 copiesChokwe(cjk)TextMT
HUHugging Face
Open20 May 2026
dataset

FLORES-200 (cpp_Latn)

Guinea-Bissau Creole (cpp_Latn) in 200-language MT benchmark

59 languages4 copiesGuinea-Bissau Creole(cpp)TextMT
HUHugging Face
Open21 May 2026
dataset

FLORES-200 / FLORES+ (dik_Latn)

FLORES-200 parallel MT evaluation corpus includes Southwestern Dinka (dik_Latn). 3001 sentences, dev/devtest splits. First large-scale MT eval coverage for d…

59 languages4 copiesDinka (Southwestern)(dik)TextMT
HUHugging Face
Open25 May 2026
dataset

Flores-200 (Facebook NLLB)

No Language Left Behind seed data with dyu coverage for machine translation

59 languages4 copiesDyula(dyu)TextMT
HUHugging Face
Open15 Jun 2026
dataset

flores

Data format: parquet

59 languages4 copiesEwe(ewe)Tabulartext-generation, translation
HUHugging Face
Open27 Oct 2026
dataset

flores

Data format: parquet

59 languages4 copiesFon(fon)Tabulartext-generation, translation
HUHugging Face
Open27 Oct 2026
dataset

FLORES-200 - Nigerian Fulfulde

Exact licence is CC-BY-SA-4.0, which is not available in the requested licence dropdown; dev and devtest total 2,009 sentences.

59 languages4 copiesNigerian Fulfulde(fuv)TextMT
HUHugging Face
Open3 Jun 2026
dataset

flores

Data format: parquet

59 languages4 copiesWest Central Oromo(gaz)Tabulartext-generation, translation
HUHugging Face
Open27 Oct 2026
dataset

flores

Data format: parquet

59 languages4 copiesHausa(hau)Tabulartext-generation, translation
HUHugging Face
Open27 Oct 2026
dataset

flores

Data format: parquet

59 languages4 copiesIgbo(ibo)Tabulartext-generation, translation
HUHugging Face
Open27 Oct 2026

Related Datasets

dataset

FLORES-200 (facebook/flores)

Original FLORES-200 evaluation set covering nus among 200+ languages; HuggingFace card explicitly states this repo 'is no longer being updated' and points to…

59 languages4 copiesNuer(nus)TextMT
HUHugging Face
Open31 Jul 2026
dataset

FLORES+ (openlanguagedata/flores_plus)

Current, actively maintained successor to facebook/flores, managed by the community-run Open Language Data Initiative. Includes nus among 200+ languages with…

60 languagesNuer(nus)TextMT
HUHugging Face
Open31 Jul 2026
dataset

SIB-200

Largest publicly available topic-classification dataset based on FLORES-200 text, covering 200+ languages/dialects including nus. Paper: 'SIB-200: A Simple, …

5 languages2 copiesNuer(nus)TextClassification
HUHugging Face
Open31 Jul 2026